1
|
Magana-Salgado U, Namburi P, Feigin-Almon M, Pallares-Lopez R, Anthony B. A comparison of point-tracking algorithms in ultrasound videos from the upper limb. Biomed Eng Online 2023; 22:52. [PMID: 37226240 DOI: 10.1186/s12938-023-01105-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Accepted: 04/25/2023] [Indexed: 05/26/2023] Open
Abstract
Tracking points in ultrasound (US) videos can be especially useful to characterize tissues in motion. Tracking algorithms that analyze successive video frames, such as variations of Optical Flow and Lucas-Kanade (LK), exploit frame-to-frame temporal information to track regions of interest. In contrast, convolutional neural-network (CNN) models process each video frame independently of neighboring frames. In this paper, we show that frame-to-frame trackers accumulate error over time. We propose three interpolation-like methods to combat error accumulation and show that all three methods reduce tracking errors in frame-to-frame trackers. On the neural-network end, we show that a CNN-based tracker, DeepLabCut (DLC), outperforms all four frame-to-frame trackers when tracking tissues in motion. DLC is more accurate than the frame-to-frame trackers and less sensitive to variations in types of tissue movement. The only caveat found with DLC comes from its non-temporal tracking strategy, leading to jitter between consecutive frames. Overall, when tracking points in videos of moving tissue, we recommend using DLC when prioritizing accuracy and robustness across movements in videos, and using LK with the proposed error-correction methods for small movements when tracking jitter is unacceptable.
Collapse
Affiliation(s)
- Uriel Magana-Salgado
- Department of Mechanical Engineering, MIT, Cambridge, MA, 02139, USA
- Mechanical Engineering Graduate Program, MIT, Cambridge, MA, 02139, USA
| | - Praneeth Namburi
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, 12-3211, Cambridge, MA, 02139, USA.
- MIT.Nano Immersion Lab, MIT, Cambridge, MA, 02139, USA.
| | | | - Roger Pallares-Lopez
- Department of Mechanical Engineering, MIT, Cambridge, MA, 02139, USA
- Mechanical Engineering Graduate Program, MIT, Cambridge, MA, 02139, USA
| | - Brian Anthony
- Department of Mechanical Engineering, MIT, Cambridge, MA, 02139, USA
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 77 Massachusetts Ave, 12-3211, Cambridge, MA, 02139, USA
- MIT.Nano Immersion Lab, MIT, Cambridge, MA, 02139, USA
| |
Collapse
|
2
|
Hunter S, Werth J, James D, Lambrianides Y, Smith K, Karamanidis K, Epro G. Reliability and Accuracy of a Time-Efficient Method for the Assessment of Achilles Tendon Mechanical Properties by Ultrasonography. SENSORS 2022; 22:s22072549. [PMID: 35408164 PMCID: PMC9002634 DOI: 10.3390/s22072549] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Revised: 03/23/2022] [Accepted: 03/24/2022] [Indexed: 11/16/2022]
Abstract
The assessment of the force-length relationship under mechanical loading is widely used to evaluate the mechanical properties of tendons and to gain information about their adaptation, function, and injury. This study aimed to provide a time-efficient ultrasound method for assessing Achilles tendon mechanical properties. On two days, eleven healthy young non-active adults performed eight maximal voluntary isometric ankle plantarflexion contractions on a dynamometer with simultaneous ultrasonographic recording. Maximal tendon elongation was assessed by digitizing ultrasound images at rest and at maximal tendon force. Achilles tendon stiffness index was calculated from the ratio of tendon force-to-strain. No within- and between-day differences were detected between the proposed method and manual frame by frame tracking in Achilles tendon maximal force, maximal elongation, maximal strain, and stiffness index. The overall coefficient of variation between trials ranged from 3.4% to 10.3% and average difference in tendon tracking between methods was less than 0.6% strain. Furthermore, an additional assessment demonstrated significant differences between elite athletes, healthy young, and older adults in Achilles tendon force and stiffness index. Hence, the analysis has the potential to reliably and accurately monitor changes in Achilles tendon mechanical properties due to aging and altered mechanical loading in a time-efficient manner.
Collapse
|
3
|
Feature Point Extraction and Motion Tracking of Cardiac Color Ultrasound under Improved Lucas-Kanade Algorithm. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:4959727. [PMID: 34394892 PMCID: PMC8357506 DOI: 10.1155/2021/4959727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/13/2021] [Revised: 07/13/2021] [Accepted: 07/26/2021] [Indexed: 11/17/2022]
Abstract
The purpose of this research is to study the application effect of Lucas–Kanade algorithm in right ventricular color Doppler ultrasound feature point extraction and motion tracking under the condition of scale invariant feature transform (SIFT). This study took the right ventricle as an example to analyze the extraction effect and calculation rate of SIFT algorithm and improved Lucas–Kanade algorithm. It was found that the calculation time before and after noise removal by the SIFT algorithm was 0.49 s and 0.46 s, respectively, and the number of extracted feature points was 703 and 698, respectively. The number of feature points extracted by the SIFT algorithm and the calculation time were significantly better than those of other algorithms (P < 0.01). The mean logarithm of the matching points of the SIFT algorithm for order matching and reverse order matching was 20.54 and 20.46, respectively. The calculation time and the number of feature points for the SIFT speckle tracking method were 1198.85 s and 81, respectively, and those of the optical flow method were 3274.19 s and 80, respectively. The calculation time of the SIFT speckle tracking method was significantly lower than that of the optical flow method (P < 0.05), and there was no statistical difference in the number of feature points between the SIFT speckle tracking method and the optical flow method (P > 0.05). In conclusion, the improved Lucas–Kanade algorithm based on SIFT significantly improves the accuracy of feature extraction and motion tracking of color Doppler ultrasound, which shows the value of the algorithm in the clinical application of color Doppler ultrasound.
Collapse
|
4
|
Abstract
The goal of treatment after Achilles tendon rupture (ATR) is to restore appropriate tension to the tendon, so that normal baseline strength and functional soft-tissue length can be achieved. The assessment of plantarflexion strength has shown widespread variability. The purpose of this study is to document variations in strength assessment after the treatment of ATR in the literature. A comprehensive literature review was performed. In total, 2758 articles were found on Achilles tendon rupture and Achilles tendon strength measurement. The full text of articles including strength as a functional outcome measurement in the abstract were assessed. All objective strength measurements performed were reviewed and recorded for comparison. One-hundred articles were included in our study. In 78 articles, a dynamometer was used to measure strength, whereas in 22 articles, an endurance test (n=14) or formal gait assessment (n=8) was applied. When a dynamometer was used, there was wide variability in the various methods used including the incorporation of both isokinetic (n = 65) and isometric (n = 29) exercises utilizing varying degrees of knee flexion and patient testing position. Furthermore, the number of measurements at certain angular velocities varied. This study illustrates that no general consensus exists regarding an optimal method for measuring strength after ATR. The variability creates difficulty and challenges medical professionals' ability to formulate consistent conclusions when determining functional performance outcomes. A more uniform way of measuring strength after ATR may allow for better comparisons between studies in the literature, potentially leading to a better understanding of strength. Levels of Evidence: Therapeutic, Level II.
Collapse
Affiliation(s)
- Henrik C Bäcker
- Department of Orthopedic Surgery, New York Presbyterian/Columbia University Medical Center, New York, NY
| | - Adrian J Yenchak
- Department of Orthopedic Surgery, New York Presbyterian/Columbia University Medical Center, New York, NY
| | - David P Trofa
- Department of Orthopedic Surgery, New York Presbyterian/Columbia University Medical Center, New York, NY
| | - J Turner Vosseller
- Department of Orthopedic Surgery, New York Presbyterian/Columbia University Medical Center, New York, NY
| |
Collapse
|
5
|
Lim SH, Nisar H, Thee KW, Yap VV. A novel method for tracking and analysis of EEG activation across brain lobes. Biomed Signal Process Control 2018. [DOI: 10.1016/j.bspc.2017.06.017] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
6
|
McCrum C, Oberländer KD, Epro G, Krauss P, James DC, Reeves ND, Karamanidis K. Loading rate and contraction duration effects on in vivo
human Achilles tendon mechanical properties. Clin Physiol Funct Imaging 2017; 38:517-523. [DOI: 10.1111/cpf.12472] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2017] [Accepted: 08/25/2017] [Indexed: 01/12/2023]
Affiliation(s)
- Christopher McCrum
- Department of Human Movement Science; NUTRIM School of Nutrition and Translational Research in Metabolism; Maastricht University Medical Centre+; Maastricht The Netherlands
- Institute of Movement and Sport Gerontology; German Sport University Cologne; Cologne Germany
| | - Kai D. Oberländer
- Media School; Fresenius University of Applied Science; Cologne Germany
| | - Gaspar Epro
- Sport and Exercise Science Research Centre; School of Applied Sciences; London South Bank University; London UK
| | - Peter Krauss
- Sport and Exercise Science Research Centre; School of Applied Sciences; London South Bank University; London UK
| | - Darren C. James
- Sport and Exercise Science Research Centre; School of Applied Sciences; London South Bank University; London UK
| | - Neil D. Reeves
- Faculty of Science and Engineering; School of Healthcare Science; Manchester Metropolitan University; Manchester UK
| | - Kiros Karamanidis
- Sport and Exercise Science Research Centre; School of Applied Sciences; London South Bank University; London UK
| |
Collapse
|
7
|
Chuang BI, Hsu JH, Kuo LC, Jou IM, Su FC, Sun YN. Tendon-motion tracking in an ultrasound image sequence using optical-flow-based block matching. Biomed Eng Online 2017; 16:47. [PMID: 28427411 PMCID: PMC5399340 DOI: 10.1186/s12938-017-0335-x] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2016] [Accepted: 03/30/2017] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Tendon motion, which is commonly observed using ultrasound imaging, is one of the most important features used in tendinopathy diagnosis. However, speckle noise and out-of-plane issues make the tracking process difficult. Manual tracking is usually time consuming and often yields inconsistent results between users. METHODS To automatically track tendon motion in ultrasound images, we developed a new method that combines the advantages of optical flow and multi-kernel block matching. For every pair of adjacent image frames, the optical flow is computed and used to estimate the accumulated displacement. The proposed method selects the frame interval adaptively based on this displacement. Multi-kernel block matching is then computed on the two selected frames, and, to reduce tracking errors, the detailed displacements of the frames in between are interpolated based on the optical flow results. RESULTS In the experiments, cadaver data were used to evaluate the tracking results. The mean absolute error was less than 0.05 mm. The proposed method also tracked the motion of tendons in vivo, which provides useful information for clinical diagnosis. CONCLUSION The proposed method provides a new index for adaptively determining the frame interval. Compared with other methods, the proposed method yields tracking results that are significantly more accurate.
Collapse
Affiliation(s)
- Bo-I Chuang
- Department of Computer Science and Information Engineering, 1 University Road, Tainan, 701, Taiwan
| | - Jian-Han Hsu
- Department of Computer Science and Information Engineering, 1 University Road, Tainan, 701, Taiwan
| | - Li-Chieh Kuo
- Department of Occupational Therapy, 1 University Road, Tainan, 701, Taiwan
| | - I-Ming Jou
- Department of Orthopedics, E-Da Hospital, I-Shou University, 1 E-Da Road, Jiao-Shu Village, Yan-Chao District, Kaohsiung City, 82445, Taiwan
| | - Fong-Chin Su
- Department of Biomedical Engineering, National Cheng Kung University, 1 University Road, Tainan, 701, Taiwan.
| | - Yung-Nien Sun
- Department of Computer Science and Information Engineering, 1 University Road, Tainan, 701, Taiwan.
| |
Collapse
|